Hang-Jun Ye

发表论文 35 篇 · 总被引 282 次 · h-index 8

代表论文

• DriveLaW:Unifying Planning and Video Generation in a Latent Driving World (2025 · arXiv.org · 被引 40)
• DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images (2025 · arXiv.org · 被引 22)
• VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving (2026 · arXiv.org · 被引 17)
• LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving (2026 · arXiv.org · 被引 17)
• DriveVA: Video Action Models are Zero-Shot Drivers (2026 · arXiv.org · 被引 14)
• UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving (2026 · arXiv.org · 被引 11)